<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/3a474d9d5ba1464692e2dc4269f221cd&quot; frameborder=&quot;0&quot; width=&quot;1280&quot; height=&quot;960&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>960</height><width>1280</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>960</thumbnail_height><thumbnail_width>1280</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/3a474d9d5ba1464692e2dc4269f221cd-ffe2fa370a7400ee.gif</thumbnail_url><duration>262.738</duration><title>🚨 Human-in-the-Loop Smart Contract Auditing with LLMs | Real-Time Feedback Flow (LlamaIndex + OpenAI)</title><description>In this demo, I showcase a powerful Human-in-the-Loop smart contract auditing workflow using LlamaIndex’s Workflow API and OpenAI&apos;s GPT-4o-mini.

The assistant performs an initial security audit on Solidity functions, and the human reviewer provides natural language feedback. The AI then regenerates the full audit output in real time, incorporating the feedback before proceeding—just like a real-world smart contract auditing assistant.

🛠️ Tech Stack: LlamaIndex • OpenAI • Python
🎯 Use Case: Auditing Solidity contracts with real-time expert collaboration
🤝 Flow: AI Audit → Human Feedback → Re-audit → Final Approval

👉 Try it for your auditing, education, or smart contract review pipelines. It’s modular, explainable, and audit-grade.</description></oembed>